Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
SlideShare a Scribd company logo

Acceptance sampling

•Download as PPT, PDF•
•
SIBENDU SURAJEET JENA
SIBENDU SURAJEET JENA

Acceptance sampling is a quality control technique where a random sample is taken from a lot and used to determine whether to accept or reject the entire lot. It aims to inspect a portion of items to draw a conclusion about the quality of the whole lot in a cost-effective manner. Key aspects include defining acceptance quality limits, sampling risks, developing sampling plans involving sample size and acceptance/rejection criteria, and understanding operating characteristic curves showing the probability of acceptance at different quality levels. The technique helps improve overall quality while reducing inspection costs and risks compared to 100% inspection.

1 of 24
ACCEPTANCE SAMPLING
Introduction • Quality control is an activity in which measures are taken to control quality of future output. • Sampling refers to observation of a population or lot for the purpose of obtaining some information about it. • Acceptance sampling is a quality control technique.
Acceptance sampling • Acceptance sampling is defined as sampling inspection in which decisions are made to accept or reject products or services. • It is a decision making tool by which a conclusion is reached regarding the acceptability of lot. • Statistical quality control technique, where a random sample is taken from a lot, and upon the results of the sample taken the lot will either be rejected or accepted.
Acceptance sampling • Accept Lot- Ready for customers • Reject Lot-Not suitable for customers • Statistical Process Control(SPC)-Sample and determine if in acceptable limits
Purpose: • Determine the quality level of an incoming shipment or, at the end production. • Ensure that the quality level is within the level that has been predetermined.
How is it done? • BEP = cost of inspection per item / cost of later repair due to a defective item • P = estimated proportion of defectives in the lot. • If P ≈ BEP, use acceptance sampling • If P > BEP, use 100% inspection • Problems with 100% inspection • Very expensive • When product must be destroyed to test • Inspection must be very tedious so defective items do not slip through inspection
When is it done? • When products in use could be damaged easily • When using new suppliers • When new products produced • When current supplier in question • Testing whole lot could be harmful
Method: Take sample Inspect Sample Decision Reject LotAccept lot Sample again Decision Return lot to supplier 100% inspection
Creation of an acceptance sampling plan: Step 1: Determine your AQL •Define a different AQL level for each defect type (minor, major & critical). • Inspect for each defect over the entire sample size and ensure an acceptable rate for each defect type. •In general, the following AQL’s are applied to Critical, Major & Minor Defects: •Critical – 0.1 •Major – 2.5 •Minor – 4.0
Step 2: Pick Your Risk Factors (α & β) There are 2 types of risks: •Consumer risk (β) •Producer risk (α) •Consumer Risk is the risk that your sampling plan will lead you to accept a lot of product that does not actually meet your quality standards. •Producers Risk is the risk that a sampling plan may lead to the rejection of a lot that actually does meet all quality standards.
Step 3: Know your data type To choose the correct sampling plan, you must understand the type of data you’re collecting. Your data will either be Attribute or Variable. 3.1 – Sampling Plan Standard for Attribute Data: Sampling Plans for attribute data are constructed such that you will test a sample quantity(n) of product from the overall population (N) and compare the number of non-conformances you observe (d) against a predefined acceptance number (a) & rejection number (r).
3.2 – Sampling Plan Standard for Variable Data: • Sample sizes for variable data is much smaller than that of attribute data. •These Sampling plans assume that the data is distributed Normally and rely on statistical calculations like the sample Average, Standard Deviation or Range.
Step 4 – Determine Which Sampling Plan You Want to Use •In general, there are 4 different, predefined types of sampling plans you can utilize. •Each one will have a different sent of acceptance/rejection rules and will also require a different number of samples to be tested. The 4 different types of sampling plans are: •Single Sampling Plan •Double Sampling Plan •Multiple Sampling Plan •Continuous Sampling Plan
Single sampling plan • A plan in which inspector is forced to make a decision concerning acceptability of a lot or batch on the basis of inspection of units in one sample taken from that lot. • It can be described in terms of 3 constants. • N,the lot size • n,the sample size • c,the acceptance number.c is the maximum allowable defects in sample. • If sample contains c or fewer defectives, lot will be accepted & if it contains more than c lot will be rejected.
Double sampling plan: • These are characterized by two sample size along with two sets of acceptance rejection numbers. • The two sample sizes may or may not be equal. • It can be described in terms of c1,c2,n1,n2
Multiple sampling plan: • In this 3 or more samples might be taken before a decision is reached regarding the acceptability of a lot. • It results in smaller average sample size.
Continuous sampling plan: • An extreme case of multiple sampling in which sampling might continues until the lot is exhausted. • It calls for inspection on an item by item basis. • Decision is made after each item is inspected concerning whether lot should be accepted or rejected or sampling continued. • Sampling & decision making continues until a clear cut decision is obtained either to accept or reject.
• Step 5 – Determine the Correct Sampling Quantity (n). • Step 6 – Determine Your Accept & Reject Numbers
AQL Sampling table
Operating characteristic curve • There is always a risk that your acceptance sampling will result in an incorrect decision to accept or reject. • To understand the acceptance probability associated with your acceptance plan, you can create an OC Curve to plot the acceptance probability versus the fraction non-conforming.
Operating characteristic curve The Operating Characteristic Curve is a plot of the probability of accepting a lot against the a theoretical incoming quality level, p(% nonconforming). The Probability of Acceptance Pa is plotted on the Y Axis, with the Theoretical Incoming Lot Defect Rate on the X Axis
Advantages:  Acceptance sampling eliminates or rectifies poor lots & improve overall quality of product.  Reduces inspection costs & risk.  In inspection of sample greater care will be taken so that results may be more accurate.  A rejected lot is frequently a signal to the manufacturer that the process should be improved.  It provides a no of alternative plans in which a single sample is taken, two or indefinite no of samples may be taken from a
Disadvantages: • Risk included in chance of bad lot “acceptance” and good lot “rejection” • Sample taken provides less information than 100% inspection
THANK YOU

More Related Content

Acceptance sampling

  • 2. Introduction • Quality control is an activity in which measures are taken to control quality of future output. • Sampling refers to observation of a population or lot for the purpose of obtaining some information about it. • Acceptance sampling is a quality control technique.
  • 3. Acceptance sampling • Acceptance sampling is defined as sampling inspection in which decisions are made to accept or reject products or services. • It is a decision making tool by which a conclusion is reached regarding the acceptability of lot. • Statistical quality control technique, where a random sample is taken from a lot, and upon the results of the sample taken the lot will either be rejected or accepted.
  • 4. Acceptance sampling • Accept Lot- Ready for customers • Reject Lot-Not suitable for customers • Statistical Process Control(SPC)-Sample and determine if in acceptable limits
  • 5. Purpose: • Determine the quality level of an incoming shipment or, at the end production. • Ensure that the quality level is within the level that has been predetermined.
  • 6. How is it done? • BEP = cost of inspection per item / cost of later repair due to a defective item • P = estimated proportion of defectives in the lot. • If P ≈ BEP, use acceptance sampling • If P > BEP, use 100% inspection • Problems with 100% inspection • Very expensive • When product must be destroyed to test • Inspection must be very tedious so defective items do not slip through inspection
  • 7. When is it done? • When products in use could be damaged easily • When using new suppliers • When new products produced • When current supplier in question • Testing whole lot could be harmful
  • 8. Method: Take sample Inspect Sample Decision Reject LotAccept lot Sample again Decision Return lot to supplier 100% inspection
  • 9. Creation of an acceptance sampling plan: Step 1: Determine your AQL •Define a different AQL level for each defect type (minor, major & critical). • Inspect for each defect over the entire sample size and ensure an acceptable rate for each defect type. •In general, the following AQL’s are applied to Critical, Major & Minor Defects: •Critical – 0.1 •Major – 2.5 •Minor – 4.0
  • 10. Step 2: Pick Your Risk Factors (α & β) There are 2 types of risks: •Consumer risk (β) •Producer risk (α) •Consumer Risk is the risk that your sampling plan will lead you to accept a lot of product that does not actually meet your quality standards. •Producers Risk is the risk that a sampling plan may lead to the rejection of a lot that actually does meet all quality standards.
  • 11. Step 3: Know your data type To choose the correct sampling plan, you must understand the type of data you’re collecting. Your data will either be Attribute or Variable. 3.1 – Sampling Plan Standard for Attribute Data: Sampling Plans for attribute data are constructed such that you will test a sample quantity(n) of product from the overall population (N) and compare the number of non-conformances you observe (d) against a predefined acceptance number (a) & rejection number (r).
  • 12. 3.2 – Sampling Plan Standard for Variable Data: • Sample sizes for variable data is much smaller than that of attribute data. •These Sampling plans assume that the data is distributed Normally and rely on statistical calculations like the sample Average, Standard Deviation or Range.
  • 13. Step 4 – Determine Which Sampling Plan You Want to Use •In general, there are 4 different, predefined types of sampling plans you can utilize. •Each one will have a different sent of acceptance/rejection rules and will also require a different number of samples to be tested. The 4 different types of sampling plans are: •Single Sampling Plan •Double Sampling Plan •Multiple Sampling Plan •Continuous Sampling Plan
  • 14. Single sampling plan • A plan in which inspector is forced to make a decision concerning acceptability of a lot or batch on the basis of inspection of units in one sample taken from that lot. • It can be described in terms of 3 constants. • N,the lot size • n,the sample size • c,the acceptance number.c is the maximum allowable defects in sample. • If sample contains c or fewer defectives, lot will be accepted & if it contains more than c lot will be rejected.
  • 15. Double sampling plan: • These are characterized by two sample size along with two sets of acceptance rejection numbers. • The two sample sizes may or may not be equal. • It can be described in terms of c1,c2,n1,n2
  • 16. Multiple sampling plan: • In this 3 or more samples might be taken before a decision is reached regarding the acceptability of a lot. • It results in smaller average sample size.
  • 17. Continuous sampling plan: • An extreme case of multiple sampling in which sampling might continues until the lot is exhausted. • It calls for inspection on an item by item basis. • Decision is made after each item is inspected concerning whether lot should be accepted or rejected or sampling continued. • Sampling & decision making continues until a clear cut decision is obtained either to accept or reject.
  • 18. • Step 5 – Determine the Correct Sampling Quantity (n). • Step 6 – Determine Your Accept & Reject Numbers
  • 20. Operating characteristic curve • There is always a risk that your acceptance sampling will result in an incorrect decision to accept or reject. • To understand the acceptance probability associated with your acceptance plan, you can create an OC Curve to plot the acceptance probability versus the fraction non-conforming.
  • 21. Operating characteristic curve The Operating Characteristic Curve is a plot of the probability of accepting a lot against the a theoretical incoming quality level, p(% nonconforming). The Probability of Acceptance Pa is plotted on the Y Axis, with the Theoretical Incoming Lot Defect Rate on the X Axis
  • 22. Advantages:  Acceptance sampling eliminates or rectifies poor lots & improve overall quality of product.  Reduces inspection costs & risk.  In inspection of sample greater care will be taken so that results may be more accurate.  A rejected lot is frequently a signal to the manufacturer that the process should be improved.  It provides a no of alternative plans in which a single sample is taken, two or indefinite no of samples may be taken from a
  • 23. Disadvantages: • Risk included in chance of bad lot “acceptance” and good lot “rejection” • Sample taken provides less information than 100% inspection

Editor's Notes

  1. In general, acceptance sampling is an approach to test the conformance of the products you have produced. You can either test a few items or every item in the lot. (LOT)-is the entire batch, group of items produced.
  2. (LOT)-entire batch, group of items produced.
  3. Remember your main purpose is to sentence the lot basically to life or death. You will reject or accept it but not measure the quality of the product.
  4. Certain situations will tend to favor different sampling methods.
  5. Filter is a way of preventing defects from being issued to customers, and defects coming to you from suppliers.
  6. Now you will begin to understand the variables and there meaning when doing the equating during the acceptance sampling process.
  7. These are more terms you need to know when equating, Type I and II errors are explained in the next couple slides.
  8. More basically producers risk is the chance of the suppliers shipment being rejected by the organization when the shipment is good. Consumers risk is the risk involved when sending products to consumers and assume the lot to be good, but it’s not.
  9. N is the number of products sampled. C is where you would reject a lot if percentage of defects surpassed it. OC is the graph showing the point where the lot would be accepted to.
  10. How to begin equating.
  11. Acceptance Plans- attributes variables
  12. Difference between defect and defectiveness in attributes. Definitions of attributes and variables.
  13. NOT MEASURING QUALITY, REJECTING OR ACCEPTING A LOT DEPENDING ON CERTAIN CIRCUMSTANCES.